Pavlo O. Dral
@pavlodral.bsky.social
Prof. at Xiamen University and NCU in Torun, co-founder of Aitomistic.
Researcher and educator in AI-enhanced computational chemistry.
All opinions expressed are mine and do not necessarily reflect those of my employers.
Researcher and educator in AI-enhanced computational chemistry.
All opinions expressed are mine and do not necessarily reflect those of my employers.
Just out in JPCL — our accurate ML approach for nonadiabatic coupling vectors!
This work took years — from early ML-FSSH struggles to finding physics-based descriptors (energy gradient differences) and improving MLIPs
#compchem @mbarbatti.bsky.social
doi.org/10.1021/acs....
This work took years — from early ML-FSSH struggles to finding physics-based descriptors (energy gradient differences) and improving MLIPs
#compchem @mbarbatti.bsky.social
doi.org/10.1021/acs....
A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is, therefore, a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs’ vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show that they allow learning NACs with never-before-reported accuracy of R2 exceeding 0.99. The key to success is also our new ML phase-correction procedure. We demonstrate the efficiency and robustness of our approach on a prototypical example of fully ML-driven FSSH simulations of fulvene targeting the SA-2-CASSCF(6,6) electronic structure level. This ML-FSSH dynamics leads to an accurate description of S1 decay while reducing error bars by allowing the execution of a large ensemble of trajectories. Our approach is generalizable to more states as we demonstrate for a three-state ML-FSSH simulation of methylenimmonium cation. Our implementations are available in open-source MLatom.
doi.org
November 6, 2025 at 12:42 PM
Just out in JPCL — our accurate ML approach for nonadiabatic coupling vectors!
This work took years — from early ML-FSSH struggles to finding physics-based descriptors (energy gradient differences) and improving MLIPs
#compchem @mbarbatti.bsky.social
doi.org/10.1021/acs....
This work took years — from early ML-FSSH struggles to finding physics-based descriptors (energy gradient differences) and improving MLIPs
#compchem @mbarbatti.bsky.social
doi.org/10.1021/acs....
Delighted to present our AI-driven #compchem work at ICCOC 2025, Shenzhen. Huge congrats to my PhD student Xinxin for winning the Best Poster Prize on AIQM methods — she is surely one of the brightest up-and-coming scientists!
November 1, 2025 at 2:58 AM
Delighted to present our AI-driven #compchem work at ICCOC 2025, Shenzhen. Huge congrats to my PhD student Xinxin for winning the Best Poster Prize on AIQM methods — she is surely one of the brightest up-and-coming scientists!
Nice work by my co-supervised PhD student Mateusz!
You can read the work at doi.org/10.1021/acs.... .
You can read the work at doi.org/10.1021/acs.... .
October 25, 2025 at 6:56 AM
Nice work by my co-supervised PhD student Mateusz!
You can read the work at doi.org/10.1021/acs.... .
You can read the work at doi.org/10.1021/acs.... .
Continuing the previous post, here is one of my favorite examples of how things can go wrong when you use universal #ML potentials - MD of H2. I love to show this example to my students, and it is in my online course (aitomistic.com/en/sub/course) at @aitomistic.com .
#compchem
#compchem
October 16, 2025 at 1:55 AM
Continuing the previous post, here is one of my favorite examples of how things can go wrong when you use universal #ML potentials - MD of H2. I love to show this example to my students, and it is in my online course (aitomistic.com/en/sub/course) at @aitomistic.com .
#compchem
#compchem
My talk at @Smlqc1Smlqc -2025 is now online.
This is the third SMLQC edition ( www.smlqc2025.com )!
Talk is covering #ML models for #compchem simulations, also available with #AIagents at the @aitomistic.com Hub ( aitomistic.xyz ).
youtu.be/gIpE_pqF2e4
This is the third SMLQC edition ( www.smlqc2025.com )!
Talk is covering #ML models for #compchem simulations, also available with #AIagents at the @aitomistic.com Hub ( aitomistic.xyz ).
youtu.be/gIpE_pqF2e4
SMLQC 2025, Pavlo O. Dral's talk "Universal AI Models for Ground and Excited States"
YouTube video by Prof. Pavlo O. Dral
youtu.be
October 8, 2025 at 2:29 AM
My talk at @Smlqc1Smlqc -2025 is now online.
This is the third SMLQC edition ( www.smlqc2025.com )!
Talk is covering #ML models for #compchem simulations, also available with #AIagents at the @aitomistic.com Hub ( aitomistic.xyz ).
youtu.be/gIpE_pqF2e4
This is the third SMLQC edition ( www.smlqc2025.com )!
Talk is covering #ML models for #compchem simulations, also available with #AIagents at the @aitomistic.com Hub ( aitomistic.xyz ).
youtu.be/gIpE_pqF2e4
Reposted by Pavlo O. Dral
Poster on Aitomia presented by Hassan Nawaz at #MDMM25, where @pavlodral.bsky.social also gave a talk on Aitomia.
Showcasing Aitomia's ability to autonomously design #compchem workflows with #AIagents, such as calculating reaction thermochemistry and spectra, on aitomistic.xyz
Showcasing Aitomia's ability to autonomously design #compchem workflows with #AIagents, such as calculating reaction thermochemistry and spectra, on aitomistic.xyz
October 1, 2025 at 6:27 AM
Poster on Aitomia presented by Hassan Nawaz at #MDMM25, where @pavlodral.bsky.social also gave a talk on Aitomia.
Showcasing Aitomia's ability to autonomously design #compchem workflows with #AIagents, such as calculating reaction thermochemistry and spectra, on aitomistic.xyz
Showcasing Aitomia's ability to autonomously design #compchem workflows with #AIagents, such as calculating reaction thermochemistry and spectra, on aitomistic.xyz
1/2Just came across this preprint discussing #ML potentials' failure even for H2.
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
Are neural scaling laws leading quantum chemistry astray?
Neural scaling laws are driving the machine learning community toward training ever-larger foundation models across domains, assuring high accuracy and transferable representations for extrapolative t...
arxiv.org
October 1, 2025 at 6:21 AM
1/2Just came across this preprint discussing #ML potentials' failure even for H2.
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
1/2Just came across this preprint discussing #ML potentials' failure even for H2.
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
Are neural scaling laws leading quantum chemistry astray?
Neural scaling laws are driving the machine learning community toward training ever-larger foundation models across domains, assuring high accuracy and transferable representations for extrapolative t...
arxiv.org
October 1, 2025 at 6:21 AM
1/2Just came across this preprint discussing #ML potentials' failure even for H2.
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
In my course, I have been showing this to my students already for many years, with both astonishing examples of failures of popular foundational ML models and tutorials on how to solve them.
arxiv.org/abs/2509.26397
hard work by Xinxin (the first author), she has many more such models in her library!
You can run #compchem simulations with AIQM2 as described in our tutorials: mlatom.com/docs/tutoria...
Also, online via a web browser on @aitomistic.com Hub at aitomistic.xyz (free)
You can run #compchem simulations with AIQM2 as described in our tutorials: mlatom.com/docs/tutoria...
Also, online via a web browser on @aitomistic.com Hub at aitomistic.xyz (free)
September 21, 2025 at 5:35 AM
hard work by Xinxin (the first author), she has many more such models in her library!
You can run #compchem simulations with AIQM2 as described in our tutorials: mlatom.com/docs/tutoria...
Also, online via a web browser on @aitomistic.com Hub at aitomistic.xyz (free)
You can run #compchem simulations with AIQM2 as described in our tutorials: mlatom.com/docs/tutoria...
Also, online via a web browser on @aitomistic.com Hub at aitomistic.xyz (free)
All-in-one leaning is a very handy method to learning from multiple levels of theory (and data sources in general) simultaneously. Better than alternative transfer learning in many respects. Just out in JCTC: pubs.acs.org/doi/10.1021/...
September 12, 2025 at 8:45 PM
All-in-one leaning is a very handy method to learning from multiple levels of theory (and data sources in general) simultaneously. Better than alternative transfer learning in many respects. Just out in JCTC: pubs.acs.org/doi/10.1021/...
Reposted by Pavlo O. Dral
🚀 MLatom 3.18.3 released!
Updates include:
✨ MACE-OFF model zoo interface
✨ Raman spectra plots (Python)
✨ Extended ML model for 2-photon absorption spectra
📄 Notes: mlatom.com/docs/release...
🔗 aitomistic.xyz
Updates include:
✨ MACE-OFF model zoo interface
✨ Raman spectra plots (Python)
✨ Extended ML model for 2-photon absorption spectra
📄 Notes: mlatom.com/docs/release...
🔗 aitomistic.xyz
Releases — MLatom @XACS documentation
mlatom.com
August 21, 2025 at 10:10 AM
🚀 MLatom 3.18.3 released!
Updates include:
✨ MACE-OFF model zoo interface
✨ Raman spectra plots (Python)
✨ Extended ML model for 2-photon absorption spectra
📄 Notes: mlatom.com/docs/release...
🔗 aitomistic.xyz
Updates include:
✨ MACE-OFF model zoo interface
✨ Raman spectra plots (Python)
✨ Extended ML model for 2-photon absorption spectra
📄 Notes: mlatom.com/docs/release...
🔗 aitomistic.xyz
It is always nice to see creative ways the users apply our methods and software (UAIQM & #MLatom) to solve their #compchem problems:
www.sciencedirect.com/science/arti...
You can use them online too at the @aitomistic.com
Hub.
www.sciencedirect.com/science/arti...
You can use them online too at the @aitomistic.com
Hub.
August 20, 2025 at 1:07 AM
It is always nice to see creative ways the users apply our methods and software (UAIQM & #MLatom) to solve their #compchem problems:
www.sciencedirect.com/science/arti...
You can use them online too at the @aitomistic.com
Hub.
www.sciencedirect.com/science/arti...
You can use them online too at the @aitomistic.com
Hub.
Back in 2021, I wrote about a future where computers could autonomously run & analyze #compchem simulations: shorturl.at/Vq4tq
Now, I’m thrilled to be building #AIagents that make this vision real!
Now, I’m thrilled to be building #AIagents that make this vision real!
August 19, 2025 at 11:52 AM
Back in 2021, I wrote about a future where computers could autonomously run & analyze #compchem simulations: shorturl.at/Vq4tq
Now, I’m thrilled to be building #AIagents that make this vision real!
Now, I’m thrilled to be building #AIagents that make this vision real!
MACE-OFF is a popular universal #ML potential for #compchem recently published in JACS. Is it up to the hype? In the video on YouTube, we dissect its strengths and weaknesses. You can try MACE-OFF yourself on @aitomistic.com Hub.
youtu.be/4Hv-Sus1384
youtu.be/4Hv-Sus1384
MACE-OFF: OFF or ON POINT? ML force field from JACS available on Aitomistic Hub
YouTube video by Prof. Pavlo O. Dral
youtu.be
August 16, 2025 at 7:06 AM
MACE-OFF is a popular universal #ML potential for #compchem recently published in JACS. Is it up to the hype? In the video on YouTube, we dissect its strengths and weaknesses. You can try MACE-OFF yourself on @aitomistic.com Hub.
youtu.be/4Hv-Sus1384
youtu.be/4Hv-Sus1384
AIQM2 just got published in @chemicalscience.rsc.org !
This #ML method's high speed, competitive accuracy, and robustness enable organic reaction #compchem simuls beyond what is possible with the popular DFT methods. It can be used for TS opt and dynamics, often with chem. accuracy.
This #ML method's high speed, competitive accuracy, and robustness enable organic reaction #compchem simuls beyond what is possible with the popular DFT methods. It can be used for TS opt and dynamics, often with chem. accuracy.
August 15, 2025 at 10:00 AM
AIQM2 just got published in @chemicalscience.rsc.org !
This #ML method's high speed, competitive accuracy, and robustness enable organic reaction #compchem simuls beyond what is possible with the popular DFT methods. It can be used for TS opt and dynamics, often with chem. accuracy.
This #ML method's high speed, competitive accuracy, and robustness enable organic reaction #compchem simuls beyond what is possible with the popular DFT methods. It can be used for TS opt and dynamics, often with chem. accuracy.
#AI + atomistic, #compchem, simulations evolve so fast I have to redo my hands-on materials multiple times a year 🤯
That's a continuously updated Living Course is the way to go.
That's a continuously updated Living Course is the way to go.
🆕 Pre-Register: Living Course on Aitomistic (#AI + Atomistic) #compchem 🚀
📚 Self-paced + interactive like webinars
🧪 Hands-on via Aitomistic Hub
Continuously updated by @pavlodral.bsky.social
Info & signup 👉 www.aitomistic.com/en/sub/livin...
#mlchem #aichem #ml
📚 Self-paced + interactive like webinars
🧪 Hands-on via Aitomistic Hub
Continuously updated by @pavlodral.bsky.social
Info & signup 👉 www.aitomistic.com/en/sub/livin...
#mlchem #aichem #ml
August 14, 2025 at 2:02 AM
Reposted by Pavlo O. Dral
Theoretical study on accurate and affordable molecular IR spectra calculations with the AIQM methods available on our Aitomistic Hub (aitomistic.xyz) was recently published in J. Phys. Chem. A.
Paper: doi.org/10.1021/acs....
Video recap: youtu.be/hkzM5qC8njI
#compchem #mlchem #aichem
Paper: doi.org/10.1021/acs....
Video recap: youtu.be/hkzM5qC8njI
#compchem #mlchem #aichem
July 17, 2025 at 2:03 PM
Theoretical study on accurate and affordable molecular IR spectra calculations with the AIQM methods available on our Aitomistic Hub (aitomistic.xyz) was recently published in J. Phys. Chem. A.
Paper: doi.org/10.1021/acs....
Video recap: youtu.be/hkzM5qC8njI
#compchem #mlchem #aichem
Paper: doi.org/10.1021/acs....
Video recap: youtu.be/hkzM5qC8njI
#compchem #mlchem #aichem
July 17, 2025 at 8:25 AM
Just landed in Kuala Lumpur to attend #IUPAC2025. If you are there and going to the conference dinner or otherwise want to meet - drop me a message ☺️
July 16, 2025 at 6:29 AM
Just landed in Kuala Lumpur to attend #IUPAC2025. If you are there and going to the conference dinner or otherwise want to meet - drop me a message ☺️
Reposted by Pavlo O. Dral
Did you know that you can run advanced #ML and common DFT #compchem calculations on Aitomistic Hub at www.aitomistic.xyz via simple MLatom input files?
Submitting MLatom Python scripts or launching Jupyter notebook also works!
Detailed tutorials at mlatom.com/docs .
Submitting MLatom Python scripts or launching Jupyter notebook also works!
Detailed tutorials at mlatom.com/docs .
July 14, 2025 at 3:00 AM
Did you know that you can run advanced #ML and common DFT #compchem calculations on Aitomistic Hub at www.aitomistic.xyz via simple MLatom input files?
Submitting MLatom Python scripts or launching Jupyter notebook also works!
Detailed tutorials at mlatom.com/docs .
Submitting MLatom Python scripts or launching Jupyter notebook also works!
Detailed tutorials at mlatom.com/docs .
Two of my PhD students graduated!
Lina Zhang did an incredible job of progressing the ML surface hopping dynamics.
Fuchun Ge developed novel NN methods directly predicting MD trajectories, and did lots of work on MLatom and ML potentials.
Each of them have 10+ publications!
dr-dral.com/people
Lina Zhang did an incredible job of progressing the ML surface hopping dynamics.
Fuchun Ge developed novel NN methods directly predicting MD trajectories, and did lots of work on MLatom and ML potentials.
Each of them have 10+ publications!
dr-dral.com/people
July 12, 2025 at 6:03 AM
Two of my PhD students graduated!
Lina Zhang did an incredible job of progressing the ML surface hopping dynamics.
Fuchun Ge developed novel NN methods directly predicting MD trajectories, and did lots of work on MLatom and ML potentials.
Each of them have 10+ publications!
dr-dral.com/people
Lina Zhang did an incredible job of progressing the ML surface hopping dynamics.
Fuchun Ge developed novel NN methods directly predicting MD trajectories, and did lots of work on MLatom and ML potentials.
Each of them have 10+ publications!
dr-dral.com/people
Presenting Aitomia (mlatom.com/aitomia/), available on @aitomistic.com Hub (aitomistic.xyz), at a huge MRS meeting in Xiamen.
Great conference to meet so many friends and colleagues and learn the latest trends in the field of materials design!
Great conference to meet so many friends and colleagues and learn the latest trends in the field of materials design!
July 7, 2025 at 1:22 AM
Presenting Aitomia (mlatom.com/aitomia/), available on @aitomistic.com Hub (aitomistic.xyz), at a huge MRS meeting in Xiamen.
Great conference to meet so many friends and colleagues and learn the latest trends in the field of materials design!
Great conference to meet so many friends and colleagues and learn the latest trends in the field of materials design!
when two decades of experience in computational and quantum chemistry, and machine learning meet the powerful #LLM!
It is astonishing how #AI has advanced #compchem simulations! Now you can chat with our AI assistant, Aitomia, and ask it to calculate, e.g., the IR spectrum of a molecule, which it will execute in seconds with state-of-the-art #ML models.
Try it at aitomistic.xyz with free registration!
Try it at aitomistic.xyz with free registration!
July 5, 2025 at 7:08 AM
when two decades of experience in computational and quantum chemistry, and machine learning meet the powerful #LLM!